CN114004405A - Photovoltaic power prediction method and system based on Elman neural network and satellite cloud picture - Google Patents

Photovoltaic power prediction method and system based on Elman neural network and satellite cloud picture Download PDF

Info

Publication number
CN114004405A
CN114004405A CN202111294879.1A CN202111294879A CN114004405A CN 114004405 A CN114004405 A CN 114004405A CN 202111294879 A CN202111294879 A CN 202111294879A CN 114004405 A CN114004405 A CN 114004405A
Authority
CN
China
Prior art keywords
elman
data
photovoltaic power
model
neural network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111294879.1A
Other languages
Chinese (zh)
Inventor
王元元
刘航航
司君诚
蔡言斌
刘琪
苏小向
张丹
马晓祎
李士峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongying Power Industry Bureau Of State Grid Shandong Electric Power Co
Original Assignee
Dongying Power Industry Bureau Of State Grid Shandong Electric Power Co
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Dongying Power Industry Bureau Of State Grid Shandong Electric Power Co filed Critical Dongying Power Industry Bureau Of State Grid Shandong Electric Power Co
Priority to CN202111294879.1A priority Critical patent/CN114004405A/en
Publication of CN114004405A publication Critical patent/CN114004405A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Marketing (AREA)
  • Biophysics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Water Supply & Treatment (AREA)
  • Evolutionary Biology (AREA)
  • Public Health (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention belongs to the technical field related to photovoltaic power generation, and provides a photovoltaic power prediction method and a system based on an Elman neural network and a satellite cloud picture, wherein the photovoltaic power prediction method comprises the following steps: acquiring historical electricity utilization data and satellite images of an electricity utilization system to be predicted and preprocessing the historical electricity utilization data and the satellite images; constructing an Elman dynamic recurrent neural network model, and inputting the preprocessed data for training; inputting the preprocessed data into a trained Elman model, and outputting a prediction result; carrying out high-precision extraction on the gray value of the satellite cloud picture to prepare modeling of an Elman neural network prediction model; an Elman photovoltaic power prediction model and an Elman photovoltaic power prediction algorithm which simultaneously consider historical operating data and satellite cloud picture gray values; and obtaining model error evaluation by an error calculation mode of the measured value and the actual value, thereby improving the accuracy of power prediction.

Description

Photovoltaic power prediction method and system based on Elman neural network and satellite cloud picture
Technical Field
The invention belongs to the technical field related to photovoltaic power generation, and particularly relates to a photovoltaic power prediction method and system based on an Elman neural network and a satellite cloud picture.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the accelerated progress of industrial gasification, the demand of human beings for energy is greatly increased, and especially the demand for electric energy is on a trend of rising year by year. For power generation energy, the consumption burden of disposable energy such as coal, oil, and natural gas is increased, and the problems associated with cost and pollution are particularly prominent. The photovoltaic-dominated new energy power generation is vigorously developed, but due to the instability of weather conditions, the photovoltaic power generation has strong intermittency and randomness, and challenges are caused to the planning and operation of the existing power system.
At present, the most used photovoltaic power prediction tool is mainly an artificial neural network. The Elman and BP neural networks are taken as recurrent neural networks and belong to artificial neural networks. However, the Elman neural network has higher global stability compared with the BP neural network due to the memory function of the carrying layer. In addition, the weather factor is considered, and the movement and dissipation of the cloud layer present no inertia sudden change in rainy days, so that difficulty is brought to photovoltaic power prediction. Photovoltaic power prediction by using a cloud picture starts to be explored. Cloud charts used for photovoltaic power prediction in the existing research are mainly divided into two types: ground based cloud cover and satellite cloud cover. The photovoltaic power prediction method based on the foundation cloud chart is more researched. However, the observation range of the foundation cloud picture is limited, the installation and maintenance cost is high, and the foundation cloud picture is difficult to widely apply. The satellite cloud images are relatively easy to obtain in domestic meteorological data websites and have a wide range, so that the research on photovoltaic power generation prediction based on the satellite cloud images gradually draws attention. The method mainly solves the problem of accurate prediction of photovoltaic power, improves the reliability of operation of the power system, and can reduce electricity consumption cost, energy consumption, energy conservation, emission reduction and economic benefit.
The inventor finds that in a photovoltaic power generation power prediction model, the characteristics contained in historical power generation power data are limited, while a traditional recursive network BP neural network has no dynamic characteristics, and has the defects of low convergence rate and poor global stability. The method is applied to photovoltaic power generation power prediction, so that the error is large, and the prediction precision cannot be well improved.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a photovoltaic power prediction method and system based on an Elman neural network and a satellite cloud picture, which solve the problems of limited data characteristics and global stability and effectively utilize meteorological laws so as to improve the power prediction precision.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a photovoltaic power prediction method based on an Elman neural network and a satellite cloud picture, which comprises the following steps:
acquiring historical electricity utilization data and satellite images of an electricity utilization system to be predicted and preprocessing the historical electricity utilization data and the satellite images;
constructing an Elman dynamic recurrent neural network model, and inputting the preprocessed data for training;
inputting the preprocessed data into a trained Elman model, and outputting a prediction result.
The invention provides a photovoltaic power prediction system based on an Elman neural network and a satellite cloud picture, which comprises:
the data acquisition module is configured to acquire historical electricity utilization data and satellite images of an electricity utilization system to be predicted and perform preprocessing;
the model building module is configured to build an Elman dynamic recurrent neural network model and input the preprocessed data for training;
and the photovoltaic power prediction module is configured to input the preprocessed data into the trained Elman model and output a prediction result.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the Elman neural network and satellite cloud based photovoltaic power prediction method according to the first aspect.
A fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the Elman neural network and satellite cloud based photovoltaic power prediction method according to the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
1. the method is used for extracting the gray value of the satellite cloud picture with high precision and preparing for modeling of an Elman neural network prediction model; an Elman photovoltaic power prediction model and an Elman photovoltaic power prediction algorithm which simultaneously consider historical operating data and satellite cloud picture gray values; the error evaluation of the model is obtained in an error calculation mode of the measured value and the actual value, so that the accuracy of power prediction is improved;
2. according to the invention, the satellite cloud picture and the historical power generation data are jointly used as characteristic input, so that the data set is further enriched and the prediction precision is improved to a certain extent; the Elman model which is superior to the BP model is selected, and the method has the advantages of high convergence rate and good overall stability. Meanwhile, the defects of no memory and static property of the BP model are overcome.
3. The invention discloses an innovative Elman model combining satellite data, which is applied to the field of photovoltaic power prediction. (ii) a
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a photovoltaic power prediction process of an Elman neural network according to a first embodiment of the present invention;
fig. 2(a) is an example of a satellite cloud at a time of 9 o' clock on day 21/3/month in accordance with an embodiment of the present invention;
fig. 2(b) is an example of a satellite cloud at 8 o' clock 4 month, 13 day, according to a first embodiment of the present invention;
fig. 3(a) is a grayscale image of a 3/month, 4/day, 8-point satellite cloud image according to the first embodiment of the present invention;
fig. 3(b) is a grayscale image of a satellite cloud image of 10 points and 15 points at 9 months and 9 days in the first embodiment of the invention;
fig. 3(c) is a grayscale image of a satellite cloud image of 10 points and 15 points at 22 days in 3 months in the first embodiment of the present invention;
fig. 3(d) is a grayscale image of a 4-month, 13-day, 8-point satellite cloud image according to the first embodiment of the present invention;
FIG. 4 is a statistical chart of the cluster number of each gray value interval according to the first embodiment of the present invention;
FIG. 5 is a diagram of the Elman neural network structure according to the first embodiment of the invention;
FIG. 6 is a diagram of the evaluation of the test error of model 1 according to the first embodiment of the present invention;
FIG. 7 is a graph of model 2 test error evaluation according to a first embodiment of the present invention;
fig. 8 is a histogram comparing the predicted power value with the actual value according to the first embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
It is noted that the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems according to various embodiments of the present disclosure. It should be noted that each block in the flowchart or block diagrams may represent a module, a segment, or a portion of code, which may comprise one or more executable instructions for implementing the logical function specified in the respective embodiment. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Example one
As shown in fig. 1 to 8, the present embodiment provides a photovoltaic power prediction method based on an Elman neural network and a satellite cloud map, and the present embodiment is illustrated by applying the method to a server, it is understood that the method may also be applied to a terminal, and may also be applied to a system including the terminal and the server, and is implemented by interaction between the terminal and the server. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network server, cloud communication, middleware service, a domain name service, a security service CDN, a big data and artificial intelligence platform, and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein. In this embodiment, the method includes the steps of:
step S100: acquiring historical electricity utilization data and satellite images of an electricity utilization system to be predicted and preprocessing the historical electricity utilization data and the satellite images;
data acquisition and satellite cloud picture processing, data normalization, and data set division into training data and test data.
Step S200: constructing an Elman dynamic recurrent neural network model, and inputting the preprocessed data for training;
and inputting training data into an Elman network model for model training.
Step S300: inputting the preprocessed data into a trained Elman model, and outputting a prediction result;
inputting test data into the trained model to obtain a predicted value, and performing inverse normalization to obtain a final predicted value;
and performing error calculation on the final predicted value and the actual value to obtain model error evaluation.
Specifically, step S100 includes satellite image acquisition, image graying processing, and grayscale value interval division.
Step S101: first, photovoltaic power data is derived from a certain photovoltaic power plant in the chapter area of Shandong province. The installed capacity of the photovoltaic power plant is 10MW, the occupied area is 405 mu, the annual average on-grid power generation amount is estimated to be 1200 ten thousand kWh, and equivalently, the coal is saved by 3670 tons. Historical photovoltaic power generation power data of the power plant in 2021 and 3-4 months are mainly adopted, and the time interval is 15 minutes.
The latitude of the selected area of the satellite cloud map is [117.00-118.00] and the longitude is [36-37], and the satellite cloud map comprises 512 x 450 pixel points, and the resolution is 1000 m. Selecting 8 parts in the morning: 00-10:30, and keeping the power data corresponding to the satellite cloud image data, and finally determining 103 data points. When the cloud layer is thicker, the sunlight is reflected more strongly, and the pixel value of the corresponding area is larger. And conversely, when the sky is clear, the pixel value of the corresponding area is smaller. As shown in fig. 2, examples of visible light images of the octopus region of shandong province on 3/21/2021 and 13/4/13/d, respectively.
It should be noted that the historical data is power generation power data of a power plant, and the resolution is 15 minutes. And (4) taking data of 8:00-10:30 in combination with cloud picture data. The cloud picture data is image data cut by latitude and longitude of the area where the power plant is located, and the resolution ratio is 1000 m. And taking data of 8:00-10:30 by considering the visible light image characteristics.
Step S102: then, graying processing of the image is performed. And cutting the picture according to the accurate longitude and latitude of the known power plant to obtain a satellite cloud picture with 50 x 50 pixel points. And then carrying out graying processing on the cloud image, namely that each pixel point in the pixel matrix meets the condition that R is equal to G and equal to B, and extracting the gray value of each pixel point. The invention selects four satellite cloud images at different time points for graying, and the obtained grayscale image is shown in fig. 3. The generated power Pa, Pb, Pc, and Pd at four points in time, 1840kw, 5902kw, 7169kw, and 2869kw, are known, and can be obtained: the smaller the grey value of the satellite cloud image is, the sparse cloud layer is, and the larger the generated power is; the larger the gray value is, the thicker the cloud layer is, and the smaller the generated power is.
Step S103: and finally, dividing gray value intervals. And carrying out interval clustering division on the gray values. Taking the above-mentioned four satellite cloud images as an example, the gray scale value ranges from 0 to 255, clustering division is performed for 10 intervals, and the statistical results are shown in table 1. The histogram is shown in figure 4. And displaying the result, wherein the number of the pixel points obtained by adopting interval clustering division still follows the change relation between the gray value and the power generation power, so that a method for predicting the power generation power by taking the interval clustering statistical result as model input is provided. The following description will be given with specific examples.
Table 1 is a statistical table of the number of pixels in each gray scale interval.
TABLE 1
Figure BDA0003336264230000071
Figure BDA0003336264230000081
Step S104: and (6) normalizing the data. And carrying out normalization processing on the clustering statistical result of the gray value interval and the historical generating power before the historical generating power and the satellite cloud picture gray value information network training to enable the value range to be [0,1 ].
Step S105: the data set is divided into training data and test data. 90% of the data points were used for training and 10% were used for testing the model and error evaluation.
Step S200: including model building and basic parameter selection
Step S201: the Elman neural network is a typical dynamic recurrent neural network, and compared with the BP neural network, the Elman neural network adds a carrying layer at an implicit layer. The network structure is generally divided into four layers: the structure of the input layer, the hidden layer, the receiving layer and the output layer is shown in fig. 5. Where u is the input vector, y is the output vector, x is the n-dimensional hidden layer unit vector, c is the n-dimensional feedback vector of the receiving layer, w1，w2，w3The connection weights from the bearer layer to the hidden layer, from the input layer to the hidden layer, and from the hidden layer to the output layer are respectively. The calculation formula of the network is as follows:
y(t)＝g(w3x(t)) (1)
x(t)＝f(w1c(t)+w2(u(t-1))) (2)
c(t)＝x(t-1) (3)
the input layer unit plays a role in signal transmission, and the output layer unit plays a role in weighting. The receiving layer is used to memorize the output value of the hidden layer unit at the previous moment, and can be regarded as a delay operator with a step delay. Hidden layer units typically use nonlinear excitation functions that take sigmoid. It self-couples its output to its input through the delay and store of the accepting layer. The self-connection mode makes the network sensitive to historical data, and the addition of the internal feedback network increases the capability of the network to process dynamic information, thereby achieving the purpose of dynamic modeling. Meanwhile, the system has the capability of adapting to time-varying characteristics, and the overall stability of the network is enhanced.
Step S202: the basic parameters of the Elman neural network are set as follows:
and (4) determining nodes of an input and output layer. According to the invention, the influence of satellite cloud picture information on the accuracy of the prediction model is mainly researched, so that the input nodes of different models are different according to the data volume. The input variable of the model 1 is historical generating power, so the number of nodes of an input layer is 1; the model 2 is added with the interval cluster number of the satellite cloud picture gray value, and the input layer node is 11. The outputs are the actual power at the current moment.
And ② the selection of the number of hidden layer nodes. The number of hidden layer neurons has a large influence on the performance of the neural network, and the prediction accuracy is influenced. When the number of the neurons in the hidden layer is too small, the network cannot perform comprehensive learning, and the accuracy of a prediction result is not high; when the number is too large, the learning speed is reduced, and an "overfitting" phenomenon may occur. The invention determines the number of hidden layer nodes according to an empirical formula:
Figure BDA0003336264230000091
in the formula: mh、Mi、MoThe number of nodes of the hidden layer, the input layer and the output layer is sequentially set; a is usually 1-8. According to an empirical formula, different hidden layer nodes are input in an attempt, the error value of each training is compared, and finally the hidden layer is selectedThe number of nodes is 3.
In step S300, the method specifically includes:
step S301: and inputting the test data into the trained model to obtain a predicted value, and performing inverse normalization. The inverse normalization is to convert the dimensionless pretest output by the model into a predicted value of an actual power unit, and the predicted value is used as a final predicted value.
Step S302: and performing error calculation on the final predicted value and the actual value to obtain model error evaluation.
In order to compare the influence on the prediction precision after the satellite cloud picture is added, two groups of predicted values are output and are measured by the error of the predicted values and the true values. The adopted errors are Root Mean Square Error (RMSE) and Relative Coefficient of Variation (Relative Coefficient of Variation), wherein the root mean square error is used for measuring the deviation between a predicted value and a true value and has the same dimension with the generated power; in order to eliminate dimension and more intuitively analyze the prediction precision of the model, the invention introduces a relative change coefficient, namely the ratio of the root mean square error to the average generated power. The corresponding calculation formula is as follows:
Figure BDA0003336264230000101
Figure BDA0003336264230000102
Figure BDA0003336264230000103
in the formula: piThe actual value of the photovoltaic output power is obtained; pfThe photovoltaic power predicted value is obtained; n is the total number of data;
Figure BDA0003336264230000104
RCV is a Relative Coefficient of variation (Relative Coefficient of variation) as an average value of photovoltaic power generation.
Model 1: the generated power at the next time is predicted using the generated power at the previous time, and the model test result is shown in fig. 6.
Model 2: the generated power at the previous moment and the clustering number of the gray level intervals extracted from the satellite cloud picture are used as input to predict the generated power at the next moment, and the model test result is shown in fig. 7. The predicted and actual values of power for the two models are not much different.
In order to compare the prediction accuracy of the two models more intuitively, the prediction result is shown in fig. 8. The prediction accuracy of the different models is listed in table 2. Combining the statistical results in table 2, the accuracy of model 2 is improved as a whole after adding the pixel information of the satellite cloud image, wherein the root mean square error is reduced from 191.3141 to 154.7513, and the RMSE-C is reduced from 0.05415 to 0.04010, which shows that the addition of the pixel information of the satellite cloud image is feasible and reliable for improving the accuracy. The reason is that the addition of the satellite cloud picture pixel information can reflect the solar irradiation information at the predicted moment, and the more useful information is input, the more accurate the prediction is.
TABLE 2 prediction accuracy of different models
TABLE 2
RMSE RMSE-C
Model
1 191.3141 0.05415
Model 2 142.0417 0.04010
Example two
The embodiment provides a photovoltaic power prediction system based on an Elman neural network and a satellite cloud picture, which comprises:
the data acquisition module is configured to acquire historical electricity utilization data and satellite images of an electricity utilization system to be predicted and perform preprocessing;
the model building module is configured to build an Elman dynamic recurrent neural network model and input the preprocessed data for training;
and the photovoltaic power prediction module is configured to input the preprocessed data into the trained Elman model and output a prediction result.
It should be noted here that the data acquisition module, the model building module, and the photovoltaic power prediction module correspond to steps S100 to S300 in the first embodiment, and the modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the contents disclosed in the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the Elman neural network and satellite cloud based photovoltaic power prediction method as described in the first embodiment above.
Example four
The embodiment provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement the steps of the Elman neural network and satellite cloud map-based photovoltaic power prediction method according to the embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A photovoltaic power prediction method based on an Elman neural network and a satellite cloud picture is characterized by comprising the following steps:
acquiring historical electricity utilization data and satellite images of an electricity utilization system to be predicted and preprocessing the historical electricity utilization data and the satellite images;
constructing an Elman dynamic recurrent neural network model, and inputting the preprocessed data for training;
inputting the preprocessed data into a trained Elman model, and outputting a prediction result.
2. The photovoltaic power prediction method based on the Elman neural network and the satellite cloud picture as claimed in claim 1, wherein the historical electricity consumption data and the satellite image of the electricity consumption system to be predicted are obtained and preprocessed, specifically:
acquiring historical photovoltaic power generation power data and a position satellite cloud picture of a power plant;
carrying out image graying processing on the satellite cloud picture, and carrying out interval clustering division on a gray value;
carrying out normalization processing on the gray value interval clustering division result and the historical power generation power to form a data set;
the data set is divided into training data and test data.
3. The photovoltaic power prediction method based on the Elman neural network and the satellite cloud picture as claimed in claim 1, wherein the Elman model is built, and preprocessed data are input for training, specifically:
constructing an Elman model, wherein the Elman model comprises an input layer, a hidden layer, a carrying layer and an output layer;
setting Elman model parameters;
inputting training data in the preprocessed data into an Elman model;
a well-trained Elman model is obtained.
4. The photovoltaic power prediction method based on the Elman neural network and the satellite cloud picture as claimed in claim 1, wherein the preprocessed data are input into a trained Elman model, and a prediction result is output, specifically:
inputting test data in the preprocessed data into the trained Elman model to obtain a predicted value;
carrying out reverse normalization on the predicted value to obtain the predicted value of the actual power unit;
and carrying out error calculation on the predicted value of the actual power unit and the actual photovoltaic power generation power to obtain model error evaluation.
5. The photovoltaic power prediction method based on the Elman neural network and the satellite cloud picture as claimed in claim 3, wherein the Elman model parameters are set, specifically:
determining nodes of an input layer and an output layer;
selecting the number of nodes of the hidden layer, wherein the specific formula is as follows:
Figure FDA0003336264220000021
in the formula: mh、Mi、MoThe number of nodes of the hidden layer, the input layer and the output layer is sequentially set; a is usually 1-8.
6. The photovoltaic power prediction method based on the Elman neural network and the satellite cloud picture as claimed in claim 1, wherein the error calculation is performed on the predicted value of the actual power unit and the actual photovoltaic power generation power to obtain a model error evaluation, specifically:
Figure FDA0003336264220000022
Figure FDA0003336264220000023
Figure FDA0003336264220000024
in the formula: piThe actual value of the photovoltaic output power is obtained; pfThe photovoltaic power predicted value is obtained; n is the total number of data;
Figure FDA0003336264220000025
the average value of the photovoltaic power generation power is obtained; RCV is the relative coefficient of variation.
7. The method for photovoltaic power prediction based on the Elman neural network and the satellite cloud picture as claimed in claim 2, wherein the data set is divided into training data and testing data, 90% of data points are used for training, and 10% of data points are used for testing the model and performing error evaluation.
8. A photovoltaic power prediction system based on an Elman neural network and a satellite cloud picture is characterized by comprising:
the data acquisition module is configured to acquire historical electricity utilization data and satellite images of an electricity utilization system to be predicted and perform preprocessing;
the model building module is configured to build an Elman dynamic recurrent neural network model and input the preprocessed data for training;
and the photovoltaic power prediction module is configured to input the preprocessed data into the trained Elman model and output a prediction result.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of a method for photovoltaic power prediction based on Elman neural network and satellite clouds according to any one of claims 1-7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of a method for photovoltaic power prediction based on Elman neural network and satellite cloud, as claimed in any one of claims 1-7.
CN202111294879.1A 2021-11-03 2021-11-03 Photovoltaic power prediction method and system based on Elman neural network and satellite cloud picture Pending CN114004405A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111294879.1A CN114004405A (en) 2021-11-03 2021-11-03 Photovoltaic power prediction method and system based on Elman neural network and satellite cloud picture

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111294879.1A CN114004405A (en) 2021-11-03 2021-11-03 Photovoltaic power prediction method and system based on Elman neural network and satellite cloud picture

Publications (1)

Publication Number Publication Date
CN114004405A true CN114004405A (en) 2022-02-01

Family

ID=79926899

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111294879.1A Pending CN114004405A (en) 2021-11-03 2021-11-03 Photovoltaic power prediction method and system based on Elman neural network and satellite cloud picture

Country Status (1)

Country Link
CN (1) CN114004405A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115564100A (en) * 2022-09-22 2023-01-03 济南大学 Photovoltaic power prediction method, system and equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104268638A (en) * 2014-09-11 2015-01-07 广州市香港科大***研究院 Photovoltaic power generation system power predicting method of elman-based neural network
CN106779154A (en) * 2016-11-22 2017-05-31 浙江工业大学 Area distribution formula photovoltaic power generation output forecasting method based on satellite cloud picture
CN110533063A (en) * 2019-07-17 2019-12-03 赛德雷特(珠海)航天科技有限公司 A kind of cloud amount calculation method and device based on satellite image and GMDH neural network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104268638A (en) * 2014-09-11 2015-01-07 广州市香港科大***研究院 Photovoltaic power generation system power predicting method of elman-based neural network
CN106779154A (en) * 2016-11-22 2017-05-31 浙江工业大学 Area distribution formula photovoltaic power generation output forecasting method based on satellite cloud picture
CN110533063A (en) * 2019-07-17 2019-12-03 赛德雷特(珠海)航天科技有限公司 A kind of cloud amount calculation method and device based on satellite image and GMDH neural network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
司志远等: "基于卫星云图特征区域定位的超短期光伏功率预测方法", 《高电压技术》, vol. 47, no. 4, 30 April 2021 (2021-04-30), pages 1214 - 1223 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115564100A (en) * 2022-09-22 2023-01-03 济南大学 Photovoltaic power prediction method, system and equipment

Similar Documents

Publication Publication Date Title
Wang et al. A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network
Raza et al. An ensemble framework for day-ahead forecast of PV output power in smart grids
CN109524993B (en) Wind power photovoltaic typical cycle output scene generation method for medium-long term optimization scheduling
CN107688906B (en) Multi-method fused transmission line meteorological element downscaling analysis system and method
CN114493050B (en) Multi-dimensional fusion new energy power parallel prediction method and device
CN107204615B (en) Method and system for realizing power prediction
CN112200377A (en) Photovoltaic medium-long term power generation capacity forecasting method and device based on SARIMAX model
Kaplan et al. A novel method based on Weibull distribution for short-term wind speed prediction
CN113554466A (en) Short-term power consumption prediction model construction method, prediction method and device
CN115859816A (en) Wind power minute-level prediction method and system based on CNN-LSTM algorithm
CN112862274A (en) WRF-LES and Deepar combined wind power prediction method
CN116595394A (en) Training method of wind speed correction model, wind speed prediction method, wind speed prediction equipment and medium
CN112100922A (en) Wind resource prediction method based on WRF and CNN convolutional neural network
CN113984198B (en) Shortwave radiation prediction method and system based on convolutional neural network
CN114498619A (en) Wind power prediction method and device
CN114330934A (en) Model parameter self-adaptive GRU new energy short-term power generation power prediction method
CN116029419A (en) Deep learning-based long-term new energy daily average generation power prediction method and system
CN112288140A (en) Keras-based short-term power load prediction method, storage medium and equipment
CN112001537A (en) Short-term wind power prediction method based on gray model and support vector machine
CN115238854A (en) Short-term load prediction method based on TCN-LSTM-AM
CN114692981A (en) Medium-and-long-term runoff forecasting method and system based on Seq2Seq model
CN107358059A (en) Short-term photovoltaic energy Forecasting Methodology and device
Alharbi et al. Short-term wind speed and temperature forecasting model based on gated recurrent unit neural networks
CN114004405A (en) Photovoltaic power prediction method and system based on Elman neural network and satellite cloud picture
CN117421871A (en) Offshore wind power potential evaluation method and device and computer equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination